Closed chufengt closed 2 years ago
Hi, @chufengt,
When we design LSeg, DPT is one of the state-of-the-art models for semantic segmentation. Therefore, we pick it for our architecture.
Yea, you could use other encoders, but you may change the hyperparameters based on their settings.
Hope this helps!
Hi I have a follow-up question about DPT as image encoder,
According to the Training Details section in your paper, did you use DPT as both the encoder and decoder? Where in the code can I find your implementation of DPT?
Hi, thanks for open-sourcing the code.
I have a quick question:
What's the reason for choosing DPT as the image encoder?
What should I note if I want to use other encoders (e.g., HR-Net)?